English

DeSIQ: Towards an Unbiased, Challenging Benchmark for Social Intelligence Understanding

Computation and Language 2023-10-31 v1 Artificial Intelligence

Abstract

Social intelligence is essential for understanding and reasoning about human expressions, intents and interactions. One representative benchmark for its study is Social Intelligence Queries (Social-IQ), a dataset of multiple-choice questions on videos of complex social interactions. We define a comprehensive methodology to study the soundness of Social-IQ, as the soundness of such benchmark datasets is crucial to the investigation of the underlying research problem. Our analysis reveals that Social-IQ contains substantial biases, which can be exploited by a moderately strong language model to learn spurious correlations to achieve perfect performance without being given the context or even the question. We introduce DeSIQ, a new challenging dataset, constructed by applying simple perturbations to Social-IQ. Our empirical analysis shows DeSIQ significantly reduces the biases in the original Social-IQ dataset. Furthermore, we examine and shed light on the effect of model size, model style, learning settings, commonsense knowledge, and multi-modality on the new benchmark performance. Our new dataset, observations and findings open up important research questions for the study of social intelligence.

Keywords

Cite

@article{arxiv.2310.18359,
  title  = {DeSIQ: Towards an Unbiased, Challenging Benchmark for Social Intelligence Understanding},
  author = {Xiao-Yu Guo and Yuan-Fang Li and Gholamreza Haffari},
  journal= {arXiv preprint arXiv:2310.18359},
  year   = {2023}
}

Comments

12 pages, 5 figures, EMNLP 2023 Long Paper